# -*- coding: utf-8 -*-

# from __future__ import division

import cv2

import numpy as np

import glob

import shutil

from random import shuffle

import os

import json

import re

import preprocess as pp

import training as train

import sklearn as sk

# from sklearn import svm

from scikits.learn import cross_val, datasets, decomposition, svm,LinearSVC

from sklearn.multiclass import OutputCodeClassifier

#import myapp as app

def temp_fucn():

print (j)

def temp_inv_fucn():

os.rename(url+j,url+i_uni)

# balus code

def train_scikit_svm():

tol=0.001, verbose=False)

"""

SVC and NuSVC implement the “one-against-one” approach (Knerr et al., 1990) for multi- class classification. If n_class is the number of classes, then n_class * (n_class - 1) / 2 classifiers are constructed and each one trains data from two classes. To provide a consistent interface with other classifiers, the decision_function_shape option allows to aggregate the results of the “one-against-one” classifiers to a decision function of shape (n_samples, n_classes):

>>>

>>> X = [[0], [1], [2], [3]]

>>> Y = [0, 1, 2, 3]

>>> clf = svm.SVC(decision_function_shape='ovo')

>>> clf.fit(X, Y)

SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,

decision_function_shape='ovo', degree=3, gamma='auto', kernel='rbf',

max_iter=-1, probability=False, random_state=None, shrinking=True,

tol=0.001, verbose=False)

>>> dec = clf.decision_function([[1]])

>>> dec.shape[1] # 4 classes: 4*3/2 = 6

6

>>> clf.decision_function_shape = "ovr"

>>> dec = clf.decision_function([[1]])

>>> dec.shape[1] # 4 classes

4

"""

label_list=[]

label_list.append('a')

url='train_images/'

train_set = []

s_list=sorted(os.listdir(url))

label = 0

for i in s_list:

s_list=glob.glob(url+i+'/*.png')

# if(len(s_list)>25):

if(len(s_list)>500):

file=open(url+i+'/utf8',"r")

i_uni=file.read()

i_uni=i_uni[:-1]

label_list.append(i_uni)

label+=1

else:

continue

print str(label),i,label_list[label],len(s_list)

int test=10;

for j in s_list:

if(!test-=1)

break;

img=cv2.imread(j,0)

img=pp.preprocess(img)

f =train.find_feature(img.copy())

# print len(f)

s = [label,f]

train_set.append(s)

f=open('label','w')

for l in label_list:

f.write(l+'\n')

f.close()

shuffle(train_set)

f_list = []

label = []

for t in train_set:

label.append(t[0])

f_list.append(t[1])

samples = np.array(f_list,np.float32)

responses = np.array(label,np.float32)

print 'auto training initiated'

print 'please wait.....'

svm.train(samples,responses,params=svm_params)

# svm.train_auto(samples,responses,None,None,params=svm_params)

svm.save("scikit_svm_class.xml")

def train_svm():

svm.save("svm_class.xml")

def gen_train_sample(im):

i+=1

# train.test()

# train_svm()

# url='/home/jithin/lekha_OCR_1.0/samples/t8.png'

# img=cv2.imread(url,0)

# # im,rot = pp.skew_correction(img)

# # # cv2.imshow("img",img)

# # # cv2.waitKey(0)

# # # cv2.destroyAllWindows()

# gen_train_sample(img)

# url='../samples/Scans/test2.png'

# temp_fucn()

tno=1

def make_compare_file():

# f.close()

def calculate_accuracy():

print 'ACCURACY:',100-((k/(j+1))*100)

# for tno in range(1,17):

# print 'DOC_'+str(tno)

# make_compare_file()

# calculate_accuracy()

def find_vlines(img):

return 0

def mytrain():

svm.save("svm_class.xml")

# -------purify training set ----------

def get_labellist():

return label_list

def purify_train():

# return f,g

# -----------end of purification function---

def make_modified_file():

g.close()

# def callapp():

# aap = app.simpleapp_tk(None)

# aap.title('My App')

# aap.mainloop()

# aap.OnButtonClick()

def recognize_block(im):

return string

def process_lines(url):

print string

def read_lines():

# print '=======phase1========'

# def visualize():

# for j in range(len(g)):

# if g[j]==83:

# print g[j]

# g[j]=0

# else:

# g[j]=1

# print g

# visualize()

# read_lines()

# img=cv2.imread('Example/pt2.png',0)

# cv2.imshow("img",img)

# cv2.waitKey(0)

# cv2.destroyAllWindows()

# img = pp.preprocess(img)

# im,rot = pp.skew_correction(img)

# # cv2.imshow("img",im)

# # cv2.waitKey(0)

# # cv2.destroyAllWindows()

# print recognize_block(img)

# print recognize_block(im.copy())

# mytrain()

# train_svm()

# make_compare_file()

# calculate_accuracy()

# purify_train()

# callapp()

# make_modified_file()